Shield logo for Digital Scholarship Group

Digital
Scholarship
Group

Introduction to Text Mining in Japanese

Workshop Instructors:

JUNGEUN (JUNE) LIM, Japan Digital Fellow, Japan Digital Research Center, Reischauer Institute

KATHERINE MATSUURA, Japan Digital Scholarship Librarian Japan Digital Research Center, Fung Library

Workshop summary:

Led by Jungeun “June” Lim (Japan Digital Fellow at the Reischauer Institute of Japanese Studies), this workshop will introduce participants to Japanese text mining for research in the humanities and social sciences. You will learn about common text mining methods, including text classification, text clustering, word embedding, and topic modeling, and what can be done with these methods. Common issues when dealing with Japanese textual data will also be discussed. After learning the core concepts, we will try running simple Python code together to get a taste of text mining.

This workshop is sponsored by the Japan Digital Research Center and Harvard’s Digital Scholarship Support Group (DSSG). Completion of this workshop and a supplementary assessment component qualifies as an elective towards the Certificate Program in Digital Scholarship. Please note that this workshop is limited to 20 participants with priority given to graduate students pursuing the Certificate Program in Digital Scholarship.

Basic experience in Python would be useful but not necessary. A laptop and a Google account are required.

To participate in this workshop, please register here by October 27, 2022.